CoLa3D: Composable Latent 3D Decomposition
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-03
Project page: https://master-cai.github.io/CoLa3D
Terminology
Sources
- Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View
- Coherent 3D Scene Diffusion From a Single RGB Image
- OneFormer3D: One Transformer for Unified Point Cloud Segmentation
- MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
- I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners
- Object-Centric Learning with Slot Attention
- Point-E: A System for Generating 3D Point Clouds from Complex Prompts
- DINOv3
- Illiterate DALL-E Learns to Compose
- GLASS: Guided Latent Slot Diffusion for Object-Centric Learning
- The Replica Dataset: A Digital Replica of Indoor Spaces
- Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
- TripoSR: Fast 3D Object Reconstruction from a Single Image
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
- OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion
- 3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
- Utonia: Toward One Encoder for All Point Clouds
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs